A Recurrent CNN for Automatic Detection and Classification of Coronary Artery Plaque and Stenosis in Coronary CT Angiography

Various types of atherosclerotic plaque and varying grades of stenosis could lead to different management of patients with a coronary artery disease. Therefore, it is crucial to detect and classify the type of coronary artery plaque, as well as to detect and determine the degree of coronary artery stenosis. This paper includes retrospectively collected clinically obtained coronary CT angiography (CCTA) scans of 163 patients. In these, the centerlines of the coronary arteries were extracted and used to reconstruct multi-planar reformatted (MPR) images for the coronary arteries. To define the reference standard, the presence and the type of plaque in the coronary arteries (no plaque, non-calcified, mixed, calcified), as well as the presence and the anatomical significance of coronary stenosis (no stenosis, non-significant, i.e., <50% luminal narrowing, and significant, i.e., ≥50% luminal narrowing) were manually annotated in the MPR images by identifying the start- and end-points of the segment of the artery affected by the plaque. To perform an automatic analysis, a multi-task recurrent convolutional neural network is applied on coronary artery MPR images. First, a 3D convolutional neural network is utilized to extract features along the coronary artery. Subsequently, the extracted features are aggregated by a recurrent neural network that performs two simultaneous multi-class classification tasks. In the first task, the network detects and characterizes the type of the coronary artery plaque. In the second task, the network detects and determines the anatomical significance of the coronary artery stenosis. The network was trained and tested using the CCTA images of 98 and 65 patients, respectively. For detection and characterization of coronary plaque, the method was achieved an accuracy of 0.77. For detection of stenosis and determination of its anatomical significance, the method was achieved an accuracy of 0.80. The results demonstrate that automatic detection and classification of coronary artery plaque and stenosis are feasible. This may enable automated triage of patients to those without coronary plaque and those with coronary plaque and stenosis in need for further cardiovascular workup.

[1]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Maria A. Zuluaga,et al.  Automatic detection of abnormal vascular cross-sections based on density level detection and support vector machines , 2010, International Journal of Computer Assisted Radiology and Surgery.

[3]  F. Rybicki,et al.  CAD-RADS™: Coronary Artery Disease - Reporting and Data System: An Expert Consensus Document of the Society of Cardiovascular Computed Tomography (SCCT), the American College of Radiology (ACR) and the North American Society for Cardiovascular Imaging (NASCI). Endorsed by the American College of Car , 2016, Journal of the American College of Radiology : JACR.

[4]  Stephan Achenbach,et al.  Can CT detect the vulnerable coronary plaque? , 2008, The International Journal of Cardiovascular Imaging.

[5]  Wufeng Xue,et al.  Full left ventricle quantification via deep multitask relationships learning , 2018, Medical Image Anal..

[6]  Bob D. de Vos,et al.  An evaluation of automatic coronary artery calcium scoring methods with cardiac CT using the orCaScore framework. , 2016, Medical physics.

[7]  Max A. Viergever,et al.  Automatic Calcium Scoring in Low-Dose Chest CT Using Deep Neural Networks With Dilated Convolutions , 2017, IEEE Transactions on Medical Imaging.

[8]  Theo van Walsum,et al.  Automatic Stenoses Detection , Quantification and Lumen Segmentation of the Coronary Arteries using a Two Point Centerline Extraction Scheme , 2012 .

[9]  M. Budoff,et al.  Diagnostic performance of 64-multidetector row coronary computed tomographic angiography for evaluation of coronary artery stenosis in individuals without known coronary artery disease: results from the prospective multicenter ACCURACY (Assessment by Coronary Computed Tomographic Angiography of Indi , 2008, Journal of the American College of Cardiology.

[10]  D. Berman,et al.  SCCT guidelines for the interpretation and reporting of coronary computed tomographic angiography. , 2009, Journal of cardiovascular computed tomography.

[11]  Marie-Francine Moens,et al.  A survey on the application of recurrent neural networks to statistical language modeling , 2015, Comput. Speech Lang..

[12]  Xiaolin Hu,et al.  Recurrent convolutional neural network for object recognition , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Ran Shadmi,et al.  Fully-convolutional deep-learning based system for coronary calcium score prediction from non-contrast chest CT , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[14]  Mark D. Huffman,et al.  Heart Disease and Stroke Statistics—2016 Update: A Report From the American Heart Association , 2016, Circulation.

[15]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[17]  Örjan Smedby,et al.  Vessel Segmentation Using Implicit Model-Guided Level Sets , 2012, MICCAI 2012.

[18]  Yan Yang,et al.  Quantification of coronary arterial stenoses in CTA using fuzzy distance transform , 2012, Comput. Medical Imaging Graph..

[19]  Michiel Schaap,et al.  HALE: Healthy Area of Lumen Estimation for Vessel Stenosis Quantification , 2016, MICCAI.

[20]  A. Arbab-Zadeh,et al.  Quantification of coronary arterial stenoses by multidetector CT angiography in comparison with conventional angiography methods, caveats, and implications. , 2011, JACC. Cardiovascular imaging.

[21]  Damini Dey,et al.  Automated three-dimensional quantification of noncalcified coronary plaque from coronary CT angiography: comparison with intravascular US. , 2010, Radiology.

[22]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[23]  M F Reiser,et al.  ECG-gated reconstructed multi-detector row CT coronary angiography: effect of varying trigger delay on image quality. , 2001, Radiology.

[24]  Max A. Viergever,et al.  Coronary artery centerline extraction in cardiac CT angiography using a CNN‐based orientation classifier , 2018, Medical Image Anal..

[25]  Frédéric Precioso,et al.  Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography , 2013, Medical Image Anal..

[26]  Jouke Dijkstra,et al.  FrenchCoast: Fast, Robust Extraction for the Nice CHallenge on COronary Artery Segmentation of the Tree , 2012 .

[27]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[28]  Dorin Comaniciu,et al.  Fast Automatic Detection of Calcified Coronary Lesions in 3D Cardiac CT Images , 2010, MLMI.

[29]  David A. Steinman,et al.  Robust and objective decomposition and mapping of bifurcating vessels , 2004, IEEE Transactions on Medical Imaging.

[30]  Renu Virmani,et al.  Pathology of the vulnerable plaque. , 2007, Journal of the American College of Cardiology.

[31]  Matthew J. Hausknecht,et al.  Beyond short snippets: Deep networks for video classification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Max A. Viergever,et al.  Automatic coronary artery calcium scoring in cardiac CT angiography using paired convolutional neural networks , 2016, Medical Image Anal..

[33]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Pablo Lamata,et al.  Recurrent Fully Convolutional Neural Networks for Multi-slice MRI Cardiac Segmentation , 2016, RAMBO+HVSMR@MICCAI.

[35]  B. Gersh,et al.  Chronic coronary artery disease: diagnosis and management. , 2009, Mayo Clinic proceedings.

[36]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[37]  P. Cattin,et al.  Multi-dimensional Gated Recurrent Units for the Segmentation of Biomedical 3D-Data , 2016, LABELS/DLMIA@MICCAI.

[38]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[39]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[40]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[41]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[42]  Dieter Ropers,et al.  Quantification of non-calcified coronary atherosclerotic plaques with dual-source computed tomography: comparison with intravascular ultrasound , 2009, Heart.

[43]  E. Halpern,et al.  Diagnosis of coronary stenosis with CT angiography comparison of automated computer diagnosis with expert readings. , 2011, Academic radiology.